Multilingual Pronunciat Improving Multilingual S
نویسندگان
چکیده
Multilinguality aspects are becoming increasingly important in the Automatic Speech Recognition (ASR) systems. It is apparent that coping with large variability of the speech signal is an even bigger challenge in multilingual ASR systems than it has been in conventional monolingual systems. In this paper, we address the importance of combining multilingual pronunciation modeling and acoustic model adaptation. To compensate the pronunciation variability across various speakers, multilingual pronunciation modeling method is proposed. Due to the limited processing power and memory resources available in many systems, we also propose a pruning scheme that removes pronunciation variants from the vocabulary based on the statistical scores obtained during the deployment of the system. To further compensate the mismatches between the multilingual acoustic models and the speaker's pronunciation, on-line MAP acoustic model adaptation is applied. Experimental results with 25 languages indicate the usefulness and efficiency of the joint use of these techniques both in clean and noisy conditions.
منابع مشابه
The Multilingual City: Vitality, Conflict, and Change, Edited by Lid King & Lorna Carson (2006), Multilingual Matters, ISBN-13 978-1-78309-477-6
متن کامل
Reflections by Robert Phillipson on English in Post-Revolutionary Iran. From Indigenization to Internationalization, M. Borjian (2013) Multilingual Matters, ISBN 978-1847699091
متن کامل
Transculturation and Multilingual Lives: Writing between Languages and Cultures
This paper looks at the issues of transculturation as explored in auto and semi-autobiographical accounts of linguistic and cultural transitions. The paper also addresses a number of questions about the structure of these texts, the authors’ linguistic competences, as well as questions about the theoretical and conceptual tool which may help us to discuss the issues the writers are reflecting o...
متن کاملImproving Deliverable Speech-to-Text Systems with Multilingual Knowledge Transfer
This paper reports our recent progress on using multilingual data for improving speech-to-text (STT) systems that can be easily delivered. We continued the work BBN conducted on the use of multilingual data for improving Babel evaluation systems, but focused on training time-delay neural network (TDNN) based chain models. As done for the Babel evaluations, we used multilingual data in two ways:...
متن کاملThe Relationship between the Interpersonal Intelligence and Reading Comprehension Achievement of Iranian Bilingual and Multilingual EFL Learners
The present study aimed at investigating the relationship between interpersonal intelligence of Iranian bilingual and multilingual EFL learners and their reading comprehension achievement. To do so, 60 intermediate EFL students were selected from a group of 80 based on their OPT scores. They were non-randomly divided into two experimental groups. Data collection took place during the summer sem...
متن کامل